paper-with-me

홈 › Papers

DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications

2025-10-29 · Malaisree P, Youwai S, Kitkobsin T, Janrungautai S, Amorndechaphon D, Rojanavasu P arxiv

Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for data-efficient detection. DINOv3 features are strategically integrated at two locations: input preprocessing (P0) and mid-backbone enhancement (P3). Experimental validation demonstrates substantial improvements: Tunnel Segment Crack detection (648 images) achieves 12.4% improvement, Construction PPE (1K images) gains 13.7%, and KITTI (7K images) shows 88.6% improvement, while maintaining real-time inference (30-47 FPS). Systematic ablation across five YOLO scales and nine DINOv3 variants reveals that Medium-scale architectures achieve optimal performance with DualP0P3 integration (55.77% mAP@0.5), while Small-scale requires Triple Integration (53.63%). The 2-4x inference overhead (21-33ms versus 8-16ms baseline) remains acceptable for field deployment on NVIDIA RTX 5090. DINO-YOLO establishes state-of-the-art performance for civil engineering datasets (<10K images) while preserving computational efficiency, providing practical solutions for construction safety monitoring and infrastructure inspection in data-constrained environments.

📄 PDF Abstract BibTeX arXiv:2510.25140

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyObject Detection

Similar Papers 제목 키워드 기반

DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops

2026-02-25 · Boyang Deng, Yuzhen Lu arxiv

Developing robust models for precision vegetable weeding is currently constrained by the scarcity of large-scale, annotated weed-crop datasets. To address this limitation, this study proposes a foundational crop-weed det…

Self-Supervised LearningDomain Generalization

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms

2023-02-01 · Shihan Ma, Jidong J. Yang

This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art…

Classificationimage-classificationImage ClassificationRepresentation Learning+1

DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video

2024-03-21 · Narek Tumanyan, Assaf Singer, Shai Bagon, Tali Dekel

We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a p…

Point Tracking

SatDINO: A Deep Dive into Self-Supervised Pretraining for Remote Sensing

2025-08-29 · Jakub Straka, Ivan Gruber arxiv

Self-supervised learning has emerged as a powerful tool for remote sensing, where large amounts of unlabeled data are available. In this work, we investigate the use of DINO, a contrastive self-supervised method, for pre…

Self-Supervised LearningRepresentation Learning

DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning

2025-09-22 · ThankGod Egbe, Peng Wang, Zhihao Guo, Zidong Chen arxiv

This paper evaluates DINOv3, a recent large-scale self-supervised vision backbone, for visuomotor diffusion policy learning in robotic manipulation. We investigate whether a purely self-supervised encoder can match or su…